Attention-driven complementary information fusion network for sparse photoacoustic image reconstruction.

Sparse-view reconstruction for photoacoustic tomography combining diffusion model with model-based iteration

Photoacoustic imaging is a new imaging technology in recent years, which combines the advantages of high resolution and rich contrast of optical imaging with the advantages of high penetration depth of acoustic imaging. Photoacoustic imaging has been widely used in biomedical fields, such as brain imaging, tumor detection and so on. The signal-tonoise ratio (SNR) of image signals in photoacoustic imaging is generally low due to the limitation of laser pulse energy, electromagnetic interference in the external environment and system noise. In order to solve the problem of low SNR of photoacoustic images, we use feedforward denoising convolutional neural network to further process the obtained images, so as to obtain higher SNR images and improve image quality. We use Python language to manage the referenced Python external library through Anaconda, and build a feedforward noise-reducing convolutional neural network on Pycharm platform. We first processed and segmated a training set containing 400 images, and then used it for network training. Finally, we tested it with a series of cerebrovascular photoacoustic microscopy images. The results show that the peak signal-to-noise ratio (PSNR) of the image increases significantly before and after denoising. The experimental results verify that the feed-forward noise reduction convolutional neural network can effectively improve the quality of photoacoustic microscopic images, which provides a good foundation for the subsequent biomedical research.

SEA-Net: Structure-Enhanced Attention Network for Limited-Angle CBCT Reconstruction of Clinical Projection Data

Photoacoustic (PA) imaging has received extensive attention in the recent decade due to its ultra-high resolution in deep tissue penetration.

Photoacoustic (PA) imaging is a non-invasive modality that combines high spatial resolution with real-time molecular visualization. The development of contrast agents with high sensitivity, deep tissue penetration, and specificity remains a critical challenge. Water-Soluble chlorophyll-binding proteins (WSCPs) stand out for their tunable optical properties and biocompatibility. Among them, the Class I WSCP from Chenopodium album (CaWSCP) exhibits unique photoconversion-induced red-shifts in absorption, enabling enhanced PA imaging through complete background subtraction and improved deep tissue imaging. To further expand its functionality, CaWSCP was engineered with a SpyTag-SpyCatcher system, enabling site-specific conjugation with HER2-specific affibodies for precise molecular targeting. Experimental findings demonstrate CaWSCP's biocompatibility, photoconversion capabilities, and potential for targeted imaging, making it a promising platform for advanced biomedical applications.Clinical Relevance- The engineered CaWSCP contrast agent, with its targeting capability via the SpyTag-SpyCatcher system, improves PA imaging for non-invasive detection and monitoring of cancer and vascular disorders by enhancing resolution and minimizing background interference.

Computed tomography has made significant advances since its introduction in the early 1970s, where researchers have mainly focused on the quality of image reconstruction in the early stage. However, radiation exposure poses a health risk, prompting the demand of the lowest possible dose when carrying out CT examinations. To acquire high-quality reconstruction images with low dose radiation, CT reconstruction techniques have evolved from conventional reconstruction such as analytical and iterative reconstruction, to reconstruction methods based on artificial intelligence (AI). All these efforts are devoted to constructing high-quality images using only low doses with fast reconstruction speed. In particular, conventional reconstruction methods usually optimize one aspect, while AI-based reconstruction has finally managed to attain all goals in one shot. However, there are limitations such as the requirements on large datasets, unstable performance, and weak generalizability in AI-based reconstruction methods. This work presents the review and discussion on the classification, the commercial use, the advantages, and the limitations of AI-based image reconstruction methods in CT.

Due to light scattering by air particles, images taken under bad lighting conditions (such as haze, fog, mist, or smog) have a reduced level of visibility. One blurry image can be made visible again using single image dehazing techniques. Due to the ill-posedness of the Single image dehazing problem, it is difficult to solve. Even though, the Dark channel prior (DCP) has been the most prevalent method for image dehazing algorithms, but it suffers from huge computational time and picture quality. The accurate transmission map estimation is one of the best preferred ways to achieve the least computational time and high picture quality in DCP. Hence, this work is focused on constructing transmission map of a hazy image based on feed forward artificial neural network. The recommended method uses a feed forward ANN to conduct the transmission map straight from the minimum channel and a normalizing procedure to increase the re-covered image information. With a training set of eighty images, the network is trained by means of mean square error (MSE). The proposed method utilizing peak signal to noise ratio (PSNR) and structural similarity (SSIM) index measures are used to assess the restoration quality. The investigational conclusions have demonstrated that, the suggested method outperforms the dehazing of an input image without degrading visible quality (PSNR = 69.16, SSIM index = 0.8913). In addition, the proposed method is suited for real-time applications given the average computing time it achieves is 1.03 s.

The procedure of procurement the original image from the degraded image assumed the knowledge of the debasing factors is called as Image Restoration. The corrupted image will be considered as input and provided to the soft computing method for decreasing the noisy information from the input image in our suggested method. Nonetheless, the established output image obtained from the soft computing method will seem to be blurry with less superiority in the contrast level. This blurred information damages the function of image reconstruction. Thus, into overawed this disadvantage, we deed an Extended Kalman filter method to provide great quality reconstructed the image, in that an optimization algorithm Grey Wolf Optimization (GWO) will be used for a greater reconstructed image. The main contribution of the proposed work is to improve the image quality of reconstruction image by means of optimal Extended Kalman filter. For proving the function of our suggested method, the reconstructed image quality will be associated with the conventional methods. The restoration method was tested with different image modalities such as MRI, CT and also Ultra Sound images of the Human abdomen. The method will be applied to the functioning platform of MATLAB. The implemented restoration technique achieves the maximum Peak Signal to Noise Ratio (PSNR) and structural similarity index (SSIM) value for liver CT image are 35.10db and 0.999 and minimum Mean square error (MSE) and Mean absolute error (MAE) value for liver CT image are 7.90E-05 and 1.1281 respectively.

Objective. Cone beam CT (CBCT) typically has severe image artifacts and inaccurate HU values, which limits its application in radiation medicines. Scholars have proposed the use of cycle consistent generative adversarial network (Cycle-GAN) to address these issues. However, the generation quality of Cycle-GAN needs to be improved. This issue is exacerbated by the inherent size discrepancies between pelvic CT scans from different patients, as well as varying slice positions within the same patient, which introduce a scaling problem during training. Approach. We introduced the Enhanced Edge and Mask (EEM) approach in our structural constraint Cycle-EEM-GAN. This approach is designed to not only solve the scaling problem but also significantly improve the generation quality of the synthetic CT images. Then data from sixty pelvic patients were used to investigate the generation of synthetic CT (sCT) from CBCT. Main results. The mean absolute error (MAE), the root mean square error (RMSE), the peak signal to noise ratio (PSNR), the structural similarity index (SSIM), and spatial nonuniformity (SNU) are used to assess the quality of the sCT generated from CBCT. Compared with CBCT images, the MAE improved from 53.09 to 37.74, RMSE from 185.22 to 146.63, SNU from 0.38 to 0.35, PSNR from 24.68 to 32.33, SSIM from 0.624 to 0.981. Also, the Cycle-EEM-GAN outperformed Cycle-GAN in terms of visual evaluation and loss. Significance. Cycle-EEM-GAN has improved the quality of CBCT images, making the structural details clear while prevents image scaling during the generation process, so that further promotes the application of CBCT in radiotherapy.

In medical applications, computed tomography (CT) is widely used to evaluate various sample characteristics. However, image quality of CT reconstruction can be degraded due to artifacts. To propose and test a truncated total variation (truncation TV) model to solve the problem of large penalties for the total variation (TV) model. In this study, a truncated TV image denoising model in the fractional B-spline wavelet domain is developed to obtain the best solution. The method is validated by the analysis of CT reconstructed images of actual biological Pigeons samples. For this purpose, several indices including the peak signal-to-noise ratio (PSNR), structural similarity index (SSIM) and mean square error (MSE) are used to evaluate the quality of images. Comparing to the conventional truncated TV model that yields 22.55, 0.688 and 361.17 in PSNR, SSIM and MSE, respectively, using the proposed fractional B-spline-truncated TV model, the computed values of these evaluation indices change to 24.24, 0.898 and 244.98, respectively, indicating substantial reduction of image noise with higher PSNR and SSIM, and lower MSE. Study results demonstrate that compared with many classic image denoising methods, the new denoising algorithm proposed in this study can more effectively suppresses the reconstructed CT image artifacts while maintaining the detailed image structure.

Optoacoustic imaging (OAI) is a unique in vivo imaging technique combining deep tissue penetration with high resolution and molecular sensitivity. OAI relying on strong intrinsic contrast, such as blood hemoglobin, already shows its value in medical diagnostics. However, OAI sensitivity to current extrinsic contrast agents is insufficient and limits its role in detecting disease-related biomarkers. The recently introduced concept of photoswitching and temporal unmixing techniques for OAI allows detecting extrinsic contrast with high sensitivity, allowing the visualization of small populations of cells labeled with photoswitching proteins deep within the tissue. However, transgene modification might not be permitted in some cases, such as for diagnostic use. Therefore, it is desirable to leverage the concept of photoswitching OAI towards injectable formulations. Since photoswitchable synthetic dyes are mainly excited by blue wavelengths unsuited for imaging in tissue, we propose exploiting the addition of XTENs to photoswitching proteins towards yielding injectable agents. The addition of XTEN to a protein enhances its plasma half-life and bioavailability, thus allowing its use, for example, in targeted labeling approaches. In this pilot study, we show that intravenously injected near-infrared absorbing photoswitchable proteins, ReBphP-PCM, coupled to XTEN, allow highly sensitive optoacoustic visualization of a tumor xenograft in vivo. The sensitivity to XTENs-ReBphP-PCM determined by ex vivo analysis of labeled cells is one to two orders of magnitude beyond conventional synthetic dyes used currently in OAI. The enhanced sensitivity afforded by photoswitching OAI, in combination with the increased bioavailability and biocompatibility of XTENs-ReBphP-PCM, makes this fusion protein a promising tool for facilitating sensitive detection of biomarkers in OAI with a potential for future use in diagnostics. STATEMENT OF SIGNIFICANCE: Optoacoustic imaging (OAI) is a unique in vivo imaging technique that combines deep tissue penetration with high resolution. OAI, which relies on intrinsic contrast, such as blood hemoglobin, could already be valuable in medical diagnostics. However, the use of extrinsic contrast agents to augment disease-related biomarkers in research and diagnostics suffers from very limited sensitivity of the generated contrast agent. We present an intravenously injected photoswitchable protein, ReBphP-PCM, coupled to XTEN, allowing highly sensitive OAI. The sensitivity is one to two orders of magnitude greater than that of conventional synthetic dyes used currently in OA imaging. The high sensitivity afforded by photoswitching together with the enhanced bioavailability and biocompatibility of the XTENs-ReBphP-PCM make this a standard agent for high-quality detection of OAI with potential for clinical use.

Neurological diseases, such as stroke and brain tumor, in addition to potential mortality, can cause trouble moving, seeing, and even problems with memory and mood. Hemodynamic function is one essential indicator to evaluate neurological diseases. Conventional optical imaging techniques have greatly benefited the medical diagnosis (e.g., interrogating brain hemodynamics); however, light scattering limits the imaging depth and resolution for further clinical applications. On the other hand, photoacoustic (PA) imaging can provide multiscale spatial resolution and deep tissue penetration based on the intrinsic optical absorption and ultrasound (US) detection, suitable for assessment of in vivo hemodynamics. In addition, by using a voltage sensor or integrating with electrocorticography (ECoG) recording, PA imaging tools can be used to evaluate neural activity as well. Here, focusing on preclinical applications (i.e., animal experimental studies), we introduce recent advancements in PA imaging tools, including PA simulation and design of multiscale PA imaging systems. Technical challenges and future directions will also be discussed to expedite the translation of PA imaging technologies from bench-side to the bedside.

Photoacoustic imaging (PAI) is an emerging biomedical modality offering non-invasive, high-resolution imaging with molecular contrast. Its effectiveness for molecular imaging is improved by using external contrast agents such as dyes and nanostructures, which enable targeted imaging, deeper tissue penetration, and enhanced diagnostic accuracy. However, the clinical translation of these agents has been hindered by limitations in biocompatibility, biodegradability, and functionalization versatility. In this study, two porphyrin-free nanoscale covalent organic frameworks (nCOFs), TAPB-PDA and LZU-1, were evaluated as novel exogenous contrast agents for PAI. Their photoacoustic responses were systematically measured and compared with traditional contrast agents, such as gold nanoparticles (AuNPs) and ATTO532-labelled mesoporous silica nanoparticles. Experiments at 532 nm across a range of concentrations demonstrated strong photoacoustic signals from TAPB-PDA and LZU-1, with enhanced response at higher concentrations. Besides, both nCOFs also provided detectable signals at the NIR window at the lowest concentration, indicating a broad working range. A nonlinear model of the volume-integrated photoacoustic pressure is also provided.Furthermore, in vitro cytotoxicity assays indicated excellent nCOF biocompatibility, even at higher concentrations. Photostability tests under prolonged pulsed laser irradiation revealed that both nCOFs exhibit good resistance to photobleaching and partial signal recovery under intermittent excitation. Collectively, these findings highlight the potential of TAPB-PDA and LZU-1 nCOFs as biocompatible, biodegradable, and functionally versatile contrast agents for advanced photoacoustic imaging.

Compared with the photoacoustic imaging (PAI) in the first near-infrared window (NIR-I, 700-1000nm), the PAI in the second near-infrared window (NIR-II, 1000-1700nm) has the advantages of less background noise, deeper tissue penetration, and larger maximum permissible exposure, which has been become a research hotspot. In this review, the recent advances in nanomaterials for NIR-II PAI are summarized, including the advantages of NIR-II PAI and the applications of nanomaterials-based NIR-II PAI in biomedical field. The nanomaterials-based PA contrast agents are classified into three categories, including organic (such as assembled small molecules, conjugated polymers, semiconducting polymers, and phthalocyanines), inorganic (such as metal sulfides, noble metals, carbon nanomaterials, quantum dots, 2D transition metal carbides and nitrides [MXenes], and semimetals), or organic/inorganic hybrid nanomaterials, which are mainly used for imaging and diagnosis of tumor tissues, brain vasculature, inflammation, and other tissues, as well as the monitoring of catalytic reaction processes in vivo. Moreover, the opportunities and challenges of NIR-II PAI are also expounded.

Photoacoustic imaging has shown great potential in guiding various minimally invasive procedures by providing complementary information to ultrasound imaging, visualising critical tissue targets as well as surgical tools such as metallic needles with rich optical contrast. The use of light emitting diodes (LEDs) as excitation sources further accelerates the clinical translation of this modality due to its favorable affordability, portability, and cost-efficiency but results in the degradation of image quality associated with low pulse energy. In this work, we propose a framework based on a modified U-Net to enhance the visualisation of clinical metallic needles with a commercial LED-based photoacoustic and ultrasound imaging system. This framework included the generation of semi-synthetic datasets combining both simulated data and in vivo measurements. Evaluation of the trained neural network was performed with needle insertions into a blood-vessel-mimicking phantom, and pork joint ex vivo tissue. This deep learning-based framework significantly enhanced the visualisation of the needle with photoacoustic imaging, achieving 4.3- and 3.2-times higher signal-to-noise ratios (SNRs) compared to conventional reconstructions, which could be helpful for guiding minimally invasive procedures.